从语言到影像，从开源到 API。读懂模型能力、比较真实成本，
为你的下一个想法，找到合适的智能引擎。
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.5-9B **MLX quantization**: provided by LM Studio team using mlx_vlm 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.
译文排队中 · 当前显示来源原文
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: Qwen **Original model**: Qwen3.6-27B **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b8883 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.6-27B **MLX quantization**: provided by LM Studio team using mlx_vlm 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.6-27B **MLX quantization**: provided by LM Studio team using mlx_vlm 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.6-27B **MLX quantization**: provided by LM Studio team using mlx_vlm 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.6-27B **MLX quantization**: provided by LM Studio team using mlx_vlm 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.
译文排队中 · 当前显示来源原文
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: Qwen **Original model**: Qwen3.6-35B-A3B **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b8814 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.6-35B-A3B **MLX quantization**: provided by LM Studio team using mlx_vlm 4-bit quantized version of Qwen3.6-35B-A3B using MLX, optimized for Apple Silicon.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.6-35B-A3B **MLX quantization**: provided by LM Studio team using mlx_vlm 6-bit quantized version of Qwen3.6-35B-A3B using MLX, optimized for Apple Silicon.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.6-35B-A3B **MLX quantization**: provided by LM Studio team using mlx_vlm 8-bit quantized version of Qwen3.6-35B-A3B using MLX, optimized for Apple Silicon.
译文排队中 · 当前显示来源原文
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: Qwen **Original model**: Qwen3.8-27B **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b10430 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
译文排队中 · 当前显示来源原文
_👾 LM Studio 社区模型亮点计划。重点介绍社区中全新且值得关注的模型。欢迎在 Discord 上参与讨论_。**模型创建者**: Qwen **原始模型**: Qwen3.8-27B **MLX 量化**: 由 LM Studio 团队使用 mlx_vlm 提供。LM Studio 并非社区模型计划中所展示任何模型的创建者、发起者或所有者。每个社区模型均由第三方创建并提供。LM Studio 不认可、不支持、不声明也不保证任何社区模型的完整性、真实性、准确性或可靠性。您理解，社区模型可能会生成令人反感、有害、不准确或其他不当或具有欺骗性的内容。每个社区模型均由其创建者或实体自行承担全部责任。LM Studio 可能无法监控或控制社区模型，亦不能也不承担任何此类模型的责任。LM Studio 对社区模型的准确性、可靠性或收益不作任何担保或保证。LM Studio 进一步声明，不保证社区模型将满足您的要求、安全无中断或在任何时间或地点均可使用，或无错误、无病毒，或任何错误将被纠正等。对于因您使用或访问社区模型、下载任何社区模型，或使用 LM Studio 提供或通过 LM Studio 提供的任何其他社区模型而造成的任何损害，您将自行承担全部责任。
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.8-27B **MLX quantization**: provided by LM Studio team using mlx_vlm 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.8-27B **MLX quantization**: provided by LM Studio team using mlx_vlm 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.8-27B **MLX quantization**: provided by LM Studio team using mlx_vlm 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.
译文排队中 · 当前显示来源原文
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: Qwen **Original model**: Qwen3.8-Flash-Next **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b10662 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
译文排队中 · 当前显示来源原文
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** Qwen **Original model**: Qwen3-8B **GGUF quantization:** provided by bartowski based on `llama.cpp` release b5200 Supports both thinking and non-thinking modes withe enhanced reasoning in both for significantly enhanced mathematics, coding, and commonsense
译文排队中 · 当前显示来源原文
This model lmstudio-community/Qwen3-8B-MLX-4bit was converted to MLX format from Qwen/Qwen3-8B using mlx-lm version **0.24.0**.
译文排队中 · 当前显示来源原文
This model lmstudio-community/Qwen3-8B-MLX-8bit was converted to MLX format from Qwen/Qwen3-8B using mlx-lm version **0.24.0**.
译文排队中 · 当前显示来源原文
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** Qwen **Original model**: Qwen3-Coder-30B-A3B-Instruct **GGUF quantization:** provided by bartowski based on `llama.cpp` release b6014 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3-Coder-30B-A3B-Instruct **MLX quantization**: provided by LM Studio team using mlx_lm 4-bit quantized version of Qwen3-Coder-30B-A3B-Instruct using MLX, optimized for Apple Silicon.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3-Coder-30B-A3B-Instruct **MLX quantization**: provided by LM Studio team using mlx_lm 5-bit quantized version of Qwen3-Coder-30B-A3B-Instruct using MLX, optimized for Apple Silicon.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3-Coder-30B-A3B-Instruct **MLX quantization**: provided by LM Studio team using mlx_lm 6-bit quantized version of Qwen3-Coder-30B-A3B-Instruct using MLX, optimized for Apple Silicon.
译文排队中 · 当前显示来源原文
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3-Coder-30B-A3B-Instruct **MLX quantization**: provided by LM Studio team using mlx_lm 8-bit quantized version of Qwen3-Coder-30B-A3B-Instruct using MLX, optimized for Apple Silicon.
译文排队中 · 当前显示来源原文
可以调整厂商、分类或输入输出条件；新模型正持续收录。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。
